© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27143
    Prev
    Next
    INDEX
    Explanations

    string type or declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ادÙĬØ©
    -0.08
    اÙħÙĬØ©
    -0.08
    SimpleName
    -0.07
    REA
    -0.07
    ÑĨин
    -0.07
    Ùİاد
    -0.07
    aminer
    -0.07
    -append
    -0.07
    urface
    -0.07
    ted
    -0.07
    POSITIVE LOGITS
    óle
    0.07
     mẽ
    0.06
     PATH
    0.06
    éĻħ
    0.06
    fs
    0.06
    á»ĩt
    0.06
    outer
    0.06
    builder
    0.06
    代ä¹ĭ
    0.06
    ä¸ĭæīĭ
    0.06
    Activations Density 0.041%

    No Known Activations